{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1917977333068848, "min": 2.6402082443237305, "max": 3.2957475185394287, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43306.3125, "min": 13530.6455078125, "max": 158169.484375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 837.8333333333334, "min": 447.09090909090907, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20108.0, "min": 15848.0, "max": 24024.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.6266538308591, "min": 1194.9353948244295, "max": 1207.0691061612065, "count": 151 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2401.2533076617183, "min": 2389.870789648859, "max": 14447.667011638192, "count": 151 }, "SoccerTwos.Step.mean": { "value": 4999316.0, "min": 9762.0, "max": 4999316.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999316.0, "min": 9762.0, "max": 4999316.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007022977340966463, "min": -0.025485271587967873, "max": 0.014050145633518696, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0842757299542427, "min": -0.30582326650619507, "max": 0.2096366137266159, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006924271583557129, "min": -0.021963290870189667, "max": 0.014459749683737755, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.08309125900268555, "min": -0.263559490442276, "max": 0.2093588411808014, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16666666666666666, "min": -0.46153846153846156, "max": 0.25538461941939133, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -6.0, "max": 3.3200000524520874, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16666666666666666, "min": -0.46153846153846156, "max": 0.25538461941939133, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -6.0, "max": 3.3200000524520874, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017782730776040503, "min": 0.010634853095204259, "max": 0.023497558594681323, "count": 230 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017782730776040503, "min": 0.010634853095204259, "max": 0.023497558594681323, "count": 230 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0021994556571977835, "min": 3.3940078821477943e-09, "max": 0.004127295214372376, "count": 230 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0021994556571977835, "min": 3.3940078821477943e-09, "max": 0.004127295214372376, "count": 230 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002198218895743291, "min": 3.4266525320939914e-09, "max": 0.004125879200485846, "count": 230 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002198218895743291, "min": 3.4266525320939914e-09, "max": 0.004125879200485846, "count": 230 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 230 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 230 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 230 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 230 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 230 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 230 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687975591", "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\grant\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.22.3", "end_time_seconds": "1687988007" }, "total": 12416.350168, "count": 1, "self": 1.8330985000011424, "children": { "run_training.setup": { "total": 0.11121659999999967, "count": 1, "self": 0.11121659999999967 }, "TrainerController.start_learning": { "total": 12414.4058529, "count": 1, "self": 7.604635399937251, "children": { "TrainerController._reset_env": { "total": 4.88384059999874, "count": 25, "self": 4.88384059999874 }, "TrainerController.advance": { "total": 12401.790542800063, "count": 325582, "self": 7.669359200153849, "children": { "env_step": { "total": 5829.152205500198, "count": 325582, "self": 4502.320749599945, "children": { "SubprocessEnvManager._take_step": { "total": 1321.840709600212, "count": 325582, "self": 43.678746400265936, "children": { "TorchPolicy.evaluate": { "total": 1278.161963199946, "count": 646634, "self": 1278.161963199946 } } }, "workers": { "total": 4.9907463000413035, "count": 325582, "self": 0.0, "children": { "worker_root": { "total": 12400.825049200037, "count": 325582, "is_parallel": true, "self": 8841.817868100221, "children": { "steps_from_proto": { "total": 0.04374080000127467, "count": 50, "is_parallel": true, "self": 0.009199699998214239, "children": { "_process_rank_one_or_two_observation": { "total": 0.03454110000306043, "count": 200, "is_parallel": true, "self": 0.03454110000306043 } } }, "UnityEnvironment.step": { "total": 3558.9634402998145, "count": 325582, "is_parallel": true, "self": 177.97005819974402, "children": { "UnityEnvironment._generate_step_input": { "total": 140.0209832001042, "count": 325582, "is_parallel": true, "self": 140.0209832001042 }, "communicator.exchange": { "total": 2671.541486200588, "count": 325582, "is_parallel": true, "self": 2671.541486200588 }, "steps_from_proto": { "total": 569.4309126993782, "count": 651164, "is_parallel": true, "self": 120.91151249869262, "children": { "_process_rank_one_or_two_observation": { "total": 448.51940020068554, "count": 2604656, "is_parallel": true, "self": 448.51940020068554 } } } } } } } } } } }, "trainer_advance": { "total": 6564.9689780997105, "count": 325582, "self": 52.8018259999435, "children": { "process_trajectory": { "total": 920.9968549997599, "count": 325582, "self": 919.5985018997584, "children": { "RLTrainer._checkpoint": { "total": 1.3983531000014864, "count": 10, "self": 1.3983531000014864 } } }, "_update_policy": { "total": 5591.170297100007, "count": 230, "self": 803.101477700091, "children": { "TorchPOCAOptimizer.update": { "total": 4788.068819399916, "count": 6900, "self": 4788.068819399916 } } } } } } }, "trainer_threads": { "total": 1.2000000424450263e-06, "count": 1, "self": 1.2000000424450263e-06 }, "TrainerController._save_models": { "total": 0.1268328999994992, "count": 1, "self": 0.007371599998805323, "children": { "RLTrainer._checkpoint": { "total": 0.11946130000069388, "count": 1, "self": 0.11946130000069388 } } } } } } }